Approved for public release; distribution is unlimited. / Traditional database development has been done for a specific, self-contained purpose with no plan to share or merge the data with other databases in the future. As these systems have matured, users have realized a requirement exists to share their data. Finding common attributes among databases is a time consuming task. However, it is one that is necessary as more and more corporations and agencies consolidate operations. In terms of DoD, the requirement to consolidate systems has come about, as the various data systems used by DoD agencies and our allies need to communicate with each other for a well-coordinated operation. One alternative for achieving the desired interconnectivity is to specify the requirement for interoperability in new systems. A more practical, less costly process is to merge existing systems and consolidate the common components. This paper proposes a process for consolidating portions of data dictionaries of two existing databases. The proposed method uses commercial-off-the-shelf software in finding common attributes between multiple databases and represents an improvement in accuracy and time over previous methods.

Approved for public release; distribution is unlimited / Currently, the most common approach in developing database applications is to use an object-oriented language for the frontend module and a relational database for the backend datastore. The major disadvantage of this approach is the well-known "impedance mismatch" in which some form of mapping is required to connect the objects in the frontend and the relational tuples in the backend. Java Data Objects (JDO) technology is recently proposed Java API that eliminates the impedance mismatch. By using JDO API, the programmers deal strictly with objects. JDO hides the details of the backend datastore by providing the object-oriented view of the datastore. JDO automatically handles the mapping between the objects and the underlying data in the relational database, which is hidden from the programmer. This thesis investigates the effectiveness of JDO. Part of the analysis will develop a database application using JDO. Although JDO provides the benefits of object-orientation in design and implementation of the databases, it is not immune from problems and limitations. The thesis will also analyze the advantages and disadvantages of using JDO and discuss the areas requiring improvements in future releases. / Major, Hellenic Air Force

Many mathematical programming models of the selection of investment portfolios assume that the best portfolio at any given level of risk is the portfolio having the highest level of return. The expected level of return is defined as a linear combination of the expected returns of the individual investments contained within the portfolio,and risk is defined in terms of variance of return. This study uses Monte Carlo simulation to establish that if the estimates of the future returns on potential investments are unbiased, the steady-state return on the portfolio is overestimated by the procedure used in the standard models. Under reasonable assumptions concerning the parameters of the estimates of the various returns, this bias is quite sizeable, with the steady-state predicted return often overestimating the steady-state actual return by more than ten percentage points. In addition, it is shown that when the variances of the alternative potential investments are not all equal,a limitation on the variance of the portfolio will reduce the magnitude of the bias. In many reasonable cases, constraining the portfolio variance reduces the bias by a magnitude greater than the amount by which it reduces the predicted portfolio return, causing the steady-state actual return to rise. This implies that return cannot automatically be assumed to be a monotonic function of risk.

by Li Wai Kit. / Bibliography: leaves 170-178 / Thesis (M.Ph.)--Chinese University of Hong Kong, 1985

So, King-yan Oldfield. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1999. / Includes bibliographical references (leaves 68-70). / Abstracts in English and Chinese. / Abstract --- p.i / Acknowledgments --- p.ii / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Evolution of Communication Technologies --- p.1 / Chapter 1.2 --- The Internet --- p.2 / Chapter 1.3 --- The Distributed Virtual Environments --- p.2 / Chapter 1.3.1 --- Features of DVE --- p.3 / Chapter 1.3.2 --- Current and Potential Applications --- p.4 / Chapter 1.3.3 --- The Challenges --- p.5 / Chapter 1.4 --- Our Contributions --- p.6 / Chapter 2 --- System Architecture --- p.7 / Chapter 2.1 --- The SSDVE and MSDVE Architectures --- p.7 / Chapter 2.2 --- Issues in the MSDVE Architecture --- p.8 / Chapter 2.2.1 --- On the Server Side --- p.8 / Chapter 2.2.2 --- On the Client Side --- p.8 / Chapter 3 --- Balancing Work Load and Reducing Inter-server Communication --- p.10 / Chapter 3.1 --- Problem Formulation --- p.10 / Chapter 3.1.1 --- The Area of Interest --- p.11 / Chapter 3.1.2 --- The DVE Cells --- p.11 / Chapter 3.1.3 --- Expected Number of Avatars --- p.12 / Chapter 3.1.4 --- Cost Metrics in Different Types of Network --- p.13 / Chapter 3.1.5 --- Problem Definition --- p.14 / Chapter 3.1.6 --- Complexity --- p.18 / Chapter 3.2 --- Partitioning Algorithms --- p.19 / Chapter 3.2.1 --- A Simplified Case --- p.19 / Chapter 3.2.2 --- The General Case --- p.19 / Chapter 3.3 --- Experiments --- p.22 / Chapter 4 --- Communication Sub-graph --- p.31 / Chapter 4.1 --- Problem Formulation --- p.31 / Chapter 4.1.1 --- Optimization Metrics --- p.32 / Chapter 4.1.2 --- Design Considerations --- p.32 / Chapter 4.2 --- Communication Sub-graph Construction Algorithms --- p.34 / Chapter 4.2.1 --- The Minimum Diameter Sub-graph (MDS) --- p.34 / Chapter 4.2.2 --- The Core-based Tree (CBT) --- p.37 / Chapter 4.2.3 --- The Minimum Spanning Tree (MST) --- p.40 / Chapter 5 --- Synchronization --- p.42 / Chapter 5.1 --- Synchronization in a DVE System --- p.43 / Chapter 5.2 --- System Model --- p.46 / Chapter 5.2.1 --- Problem Definition --- p.47 / Chapter 5.2.2 --- The Markov Chain Model --- p.47 / Chapter 5.2.3 --- Deciding the Threshold Φ --- p.49 / Chapter 5.3 --- Optimal Synchronizing Interval --- p.50 / Chapter 5.3.1 --- "An ""on-average"" Guarantee" --- p.50 / Chapter 5.3.2 --- A Stochastic Guarantee --- p.52 / Chapter 5.3.3 --- Finding p with T and Φ --- p.52 / Chapter 5.3.4 --- Searching for r*p --- p.54 / Chapter 5.4 --- Experiments --- p.55 / Chapter 5.4.1 --- Simulation Results --- p.55 / Chapter 5.4.2 --- Theoretical Results --- p.58 / Chapter 6 --- Related Work --- p.63 / Chapter 6.1 --- Load Balancing on DVE --- p.63 / Chapter 6.2 --- Object State Synchronization Techniques --- p.63 / Chapter 6.3 --- Group Communication and Multicasting --- p.64 / Chapter 6.4 --- DVE System Development Toolkits --- p.64 / Chapter 6.5 --- Example DVE Systems --- p.65 / Chapter 7 --- Conclusion --- p.66 / Chapter 7.1 --- A Vision to the Future --- p.66 / Chapter 7.2 --- Conclusion --- p.66 / Bibliography --- p.68

Chan Ming-fei. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1999. / Includes bibliographical references (leaves 63-66). / Abstract --- p.i / Acknowledgments --- p.iii / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Challenging Issues --- p.2 / Chapter 1.2 --- Previous Work --- p.4 / Chapter 1.3 --- Organization of the Thesis --- p.5 / Chapter 2 --- Distributed Virtual Environment --- p.6 / Chapter 2.1 --- Possible Architectures --- p.6 / Chapter 2.2 --- Representations of Clients as Avatars --- p.7 / Chapter 2.3 --- Dynamic Membership --- p.9 / Chapter 3 --- Bandwidth and Computation Reduction Techniques --- p.11 / Chapter 3.1 --- Network Communication --- p.12 / Chapter 3.2 --- Dead Reckoning --- p.13 / Chapter 3.3 --- Message Aggregation --- p.15 / Chapter 3.3.1 --- Network-Based Aggregation --- p.15 / Chapter 3.3.2 --- Organization-Based Aggregations --- p.16 / Chapter 3.3.3 --- Grid-Based Aggregations --- p.16 / Chapter 3.4 --- Relevance Filtering --- p.17 / Chapter 3.4.1 --- Entity-Based Filtering --- p.17 / Chapter 3.4.2 --- Grid-Based Filtering --- p.19 / Chapter 3.5 --- Quiescent Entities --- p.20 / Chapter 3.6 --- Spatial Partitioning --- p.21 / Chapter 3.6.1 --- Necessity of Spatial Partitioning --- p.22 / Chapter 3.6.2 --- Binary Space Partitioning Tree --- p.23 / Chapter 3.6.3 --- BSP Tree Construction --- p.23 / Chapter 4 --- Partitioning Algorithm --- p.25 / Chapter 4.1 --- Problem Formulation --- p.25 / Chapter 4.2 --- Exhaustive Partition (EP) Algorithm --- p.28 / Chapter 4.3 --- Partitioning Algorithm --- p.29 / Chapter 4.3.1 --- Recursive Bisection Partition (RBP) Algorithm --- p.30 / Chapter 4.3.2 --- Layering Partitioning (LP) Algorithm --- p.32 / Chapter 4.3.3 --- Communication Refinement Partitioning (CRP) Algorithm --- p.38 / Chapter 4.4 --- Parallel Approach --- p.42 / Chapter 4.5 --- Further Observation --- p.43 / Chapter 5 --- Experiments --- p.44 / Chapter 5.1 --- Experiment 1: Small Virtual World --- p.45 / Chapter 5.2 --- Experiment 2: Large Virtual World --- p.46 / Chapter 5.3 --- Experiment 3: Moving of Avatars --- p.47 / Chapter 5.4 --- Experiment 4: Dynamic Joining and Leaving --- p.48 / Chapter 5.5 --- Experiment 5: Parallel Approach --- p.49 / Chapter 6 --- Implementation Considerations --- p.55 / Chapter 6.1 --- Different Environments --- p.55 / Chapter 6.2 --- Platform --- p.56 / Chapter 6.3 --- Lessons learned --- p.57 / Chapter 7 --- Conclusion --- p.59 / A Simplex Method --- p.60 / Bibliography --- p.63

by Chan Wai To. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2001. / Includes bibliographical references (leaves 117-121). / Abstracts in English and Chinese. / Abstract --- p.ii / Acknowledgments --- p.iv / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Clustering --- p.3 / Chapter 1.2 --- Mobile Agent --- p.4 / Chapter 1.3 --- Contribution --- p.4 / Chapter 1.4 --- Outline of this Thesis --- p.5 / Chapter 2 --- Related Work --- p.6 / Chapter 2.1 --- Clustering --- p.6 / Chapter 2.1.1 --- K-Means Clustering --- p.6 / Chapter 2.1.2 --- A more efficient K-Means Clustering Algorithm --- p.3 / Chapter 2.1.3 --- K-Medoids Clustering Algorithms --- p.8 / Chapter 2.1.4 --- Linkage-based Methods --- p.11 / Chapter 2.1.5 --- BIRCH --- p.13 / Chapter 2.1.6 --- DBSCAN --- p.14 / Chapter 2.1.7 --- Other Clustering Algorithm --- p.17 / Chapter 2.2 --- Parallel Clustering and Distributed Clustering --- p.17 / Chapter 2.2.1 --- A Fast Parallel Clustering Algorithm for Large Spatial Databases --- p.17 / Chapter 2.3 --- Distributed Data Mining --- p.18 / Chapter 2.3.1 --- A Distributed Clustering Algorithm --- p.18 / Chapter 2.3.2 --- Efficient Mining of Association Rules in Distributed Databases --- p.19 / Chapter 2.4 --- Information Retrieval and Document Clustering --- p.20 / Chapter 2.4.1 --- Document and Document Set Representation --- p.20 / Chapter 2.4.2 --- TFIDF --- p.20 / Chapter 2.4.3 --- Similarity --- p.21 / Chapter 2.4.4 --- Partitional Document Clustering --- p.22 / Chapter 2.4.5 --- Hierarchical Document Clustering --- p.22 / Chapter 2.4.6 --- Document Clustering Application --- p.23 / Chapter 3 --- Distributed Clustering --- p.24 / Chapter 3.1 --- Problem Description --- p.24 / Chapter 3.2 --- Distributed k-Means Clustering Algorithm --- p.25 / Chapter 3.2.1 --- Initialization --- p.25 / Chapter 3.2.2 --- weighted k-Means procedure --- p.26 / Chapter 3.2.3 --- Refinement --- p.27 / Chapter 3.2.4 --- Example --- p.31 / Chapter 3.2.5 --- Communication Cost --- p.34 / Chapter 3.3 --- Grid k-Mean --- p.34 / Chapter 3.3.1 --- Runtime Splitting --- p.36 / Chapter 3.3.2 --- Initial Clusters --- p.38 / Chapter 3.3.3 --- Refinement --- p.38 / Chapter 3.3.4 --- Overall Algorithm --- p.39 / Chapter 3.3.5 --- Efficiency in Decomposition --- p.42 / Chapter 3.3.6 --- Example --- p.42 / Chapter 3.3.7 --- Comparison with previous k-Means method --- p.43 / Chapter 3.3.8 --- Communication Cost --- p.44 / Chapter 3.4 --- Experiment --- p.44 / Chapter 3.4.1 --- Performance --- p.46 / Chapter 3.4.2 --- Communication Cost --- p.47 / Chapter 3.4.3 --- Quality of Clustering --- p.49 / Chapter 3.4.4 --- Clustering in High Dimension --- p.49 / Chapter 3.4.5 --- Other Data Distributions --- p.52 / Chapter 4 --- Distributed DBSCAN --- p.54 / Chapter 4.1 --- Representative points of local candidate clusters --- p.55 / Chapter 4.2 --- Verification and Cluster Merging --- p.57 / Chapter 4.2.1 --- Clustering Result Quality --- p.59 / Chapter 4.3 --- Experiment --- p.62 / Chapter 5 --- Document Clustering --- p.72 / Chapter 5.1 --- Initialization --- p.73 / Chapter 5.2 --- Refinement --- p.76 / Chapter 5.3 --- Stopping criteria --- p.77 / Chapter 5.4 --- Message --- p.77 / Chapter 5.5 --- Algorithm --- p.78 / Chapter 5.6 --- Experiment --- p.82 / Chapter 5.6.1 --- Data Source and Experimental Setup --- p.82 / Chapter 5.6.2 --- Data Size --- p.34 / Chapter 5.6.3 --- Evaluation Metrics --- p.85 / Chapter 5.6.4 --- Experimental Result --- p.85 / Chapter 5.6.5 --- Comparison to Other Algorithms --- p.94 / Chapter 5.6.6 --- Conclusion --- p.94 / Chapter 5.7 --- Future Work --- p.95 / Chapter 6 --- Agent and Implementation Details --- p.96 / Chapter 6.1 --- Agent Introduction --- p.96 / Chapter 6.1.1 --- Reason to use Mobile Agent --- p.97 / Chapter 6.1.2 --- Grasshopper Overview --- p.97 / Chapter 6.1.3 --- Agent Scenario --- p.98 / Chapter 6.1.4 --- Another Agent Scenario --- p.99 / Chapter 6.2 --- Implementation Details --- p.100 / Chapter 6.2.1 --- Distributed k-Means --- p.100 / Chapter 6.2.2 --- Grid k-Means --- p.104 / Chapter 6.2.3 --- Distributed DBSCAN --- p.109 / Chapter 6.2.4 --- Distributed Document Clustering --- p.112 / Chapter 7 --- Conclusion

Typescript (photocopy). / Digitized by Kansas Correctional Industries

Typescript, etc. / Digitized by Kansas Correctional Industries

Typescript, etc. / Digitized by Kansas Correctional Industries